[go: up one dir, main page]

WO2014140541A3 - Signal processing systems - Google Patents

Signal processing systems Download PDF

Info

Publication number
WO2014140541A3
WO2014140541A3 PCT/GB2014/050695 GB2014050695W WO2014140541A3 WO 2014140541 A3 WO2014140541 A3 WO 2014140541A3 GB 2014050695 W GB2014050695 W GB 2014050695W WO 2014140541 A3 WO2014140541 A3 WO 2014140541A3
Authority
WO
WIPO (PCT)
Prior art keywords
category
output example
output
probability vector
probability
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/GB2014/050695
Other languages
French (fr)
Other versions
WO2014140541A2 (en
Inventor
Julien Robert Michel CORNEBISE
Danilo Jimenez REZENDE
Daniël Pieter WIERSTRA
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Google LLC
Original Assignee
Google LLC
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Google LLC filed Critical Google LLC
Priority to CN201480016209.5A priority Critical patent/CN105144203B/en
Priority to EP14715977.6A priority patent/EP2973241B1/en
Publication of WO2014140541A2 publication Critical patent/WO2014140541A2/en
Publication of WO2014140541A3 publication Critical patent/WO2014140541A3/en
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/0475—Generative networks
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/0495—Quantised networks; Sparse networks; Compressed networks
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/0499—Feedforward networks
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/0895—Weakly supervised learning, e.g. semi-supervised or self-supervised learning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/09—Supervised learning

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Molecular Biology (AREA)
  • Artificial Intelligence (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Image Analysis (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

We describe a signal processor, the signal processor comprising: a probability vector generation system, wherein said probability vector generation system has an input to receive a category vector for a category of output example and an output to provide a probability vector for said category of output example, wherein said output example comprises a set of data points, and wherein said probability vector defines a probability of each of said set of data points for said category of output example; a memory storing a plurality of said category vectors, one for each of a plurality of said categories of output example; and a stochastic selector to select a said stored category of output example for presentation of the corresponding category vector to said probability vector generation system; wherein said signal processor is configured to output data for an output example corresponding to said selected stored category.
PCT/GB2014/050695 2013-03-15 2014-03-10 Signal processing systems Ceased WO2014140541A2 (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN201480016209.5A CN105144203B (en) 2013-03-15 2014-03-10 Signal processing system
EP14715977.6A EP2973241B1 (en) 2013-03-15 2014-03-10 Signal processing systems

Applications Claiming Priority (4)

Application Number Priority Date Filing Date Title
GB1304795.6 2013-03-15
GB1304795.6A GB2513105A (en) 2013-03-15 2013-03-15 Signal processing systems
US13/925,637 US9342781B2 (en) 2013-03-15 2013-06-24 Signal processing systems
US13/925,637 2013-06-24

Publications (2)

Publication Number Publication Date
WO2014140541A2 WO2014140541A2 (en) 2014-09-18
WO2014140541A3 true WO2014140541A3 (en) 2015-03-19

Family

ID=48226490

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/GB2014/050695 Ceased WO2014140541A2 (en) 2013-03-15 2014-03-10 Signal processing systems

Country Status (5)

Country Link
US (1) US9342781B2 (en)
EP (1) EP2973241B1 (en)
CN (1) CN105144203B (en)
GB (1) GB2513105A (en)
WO (1) WO2014140541A2 (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107291690A (en) * 2017-05-26 2017-10-24 北京搜狗科技发展有限公司 Punctuate adding method and device, the device added for punctuate

Families Citing this family (31)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR102366783B1 (en) * 2014-07-07 2022-02-24 광주과학기술원 Neuromorphic system operating method therefor
WO2017122785A1 (en) * 2016-01-15 2017-07-20 Preferred Networks, Inc. Systems and methods for multimodal generative machine learning
US9802599B2 (en) * 2016-03-08 2017-10-31 Ford Global Technologies, Llc Vehicle lane placement
EP3444758B1 (en) * 2016-04-15 2021-11-17 Cambricon Technologies Corporation Limited Discrete data representation-supporting apparatus and method for back-training of artificial neural network
EP3451240A4 (en) * 2016-04-27 2020-01-01 Cambricon Technologies Corporation Limited Apparatus and method for performing auto-learning operation of artificial neural network
EP3459017B1 (en) 2016-05-20 2023-11-01 Deepmind Technologies Limited Progressive neural networks
US9779355B1 (en) 2016-09-15 2017-10-03 International Business Machines Corporation Back propagation gates and storage capacitor for neural networks
WO2018085697A1 (en) * 2016-11-04 2018-05-11 Google Llc Training neural networks using a variational information bottleneck
CN110383299B (en) 2017-02-06 2023-11-17 渊慧科技有限公司 Memory-augmented generation time model
KR102410820B1 (en) * 2017-08-14 2022-06-20 삼성전자주식회사 Method and apparatus for recognizing based on neural network and for training the neural network
WO2019098644A1 (en) * 2017-11-17 2019-05-23 삼성전자주식회사 Multimodal data learning method and device
KR102387305B1 (en) * 2017-11-17 2022-04-29 삼성전자주식회사 Method and device for learning multimodal data
CN110110853B (en) * 2018-02-01 2021-07-30 赛灵思电子科技(北京)有限公司 Deep neural network compression method and device and computer readable medium
CN108388446A (en) 2018-02-05 2018-08-10 上海寒武纪信息科技有限公司 Computing module and method
JP6601644B1 (en) * 2018-08-03 2019-11-06 Ｌｉｎｎｅ株式会社 Image information display device
JP7063230B2 (en) * 2018-10-25 2022-05-09 トヨタ自動車株式会社 Communication device and control program for communication device
EP3857324B1 (en) * 2018-10-29 2022-09-14 Siemens Aktiengesellschaft Dynamically refining markers in an autonomous world model
US12293292B2 (en) * 2019-03-12 2025-05-06 Samsung Electronics Co., Ltd Multiple-input multiple-output (MIMO) detector selection using neural network
US12008478B2 (en) 2019-10-18 2024-06-11 Unlearn.AI, Inc. Systems and methods for training generative models using summary statistics and other constraints
CN111127179B (en) * 2019-12-12 2023-08-29 恩亿科(北京)数据科技有限公司 Information pushing method, device, computer equipment and storage medium
US11823060B2 (en) * 2020-04-29 2023-11-21 HCL America, Inc. Method and system for performing deterministic data processing through artificial intelligence
US20210374524A1 (en) * 2020-05-31 2021-12-02 Salesforce.Com, Inc. Systems and Methods for Out-of-Distribution Detection
US11868428B2 (en) * 2020-07-21 2024-01-09 Samsung Electronics Co., Ltd. Apparatus and method with compressed neural network computation
EP3975038A1 (en) * 2020-09-29 2022-03-30 Robert Bosch GmbH An image generation model based on log-likelihood
DE102020212515A1 (en) * 2020-10-02 2022-04-07 Robert Bosch Gesellschaft mit beschränkter Haftung Method and device for training a machine learning system
CN112348158B (en) * 2020-11-04 2024-02-13 重庆大学 Industrial equipment state evaluation method based on multi-parameter deep distribution learning
WO2022182905A1 (en) * 2021-02-24 2022-09-01 Protopia AI, Inc. Stochastic noise layers
US20230073226A1 (en) * 2021-09-09 2023-03-09 Yahoo Assets Llc System and method for bounding means of discrete-valued distributions
WO2024107461A1 (en) * 2022-11-16 2024-05-23 Unlearn.AI, Inc. Systems and methods for supplementing data with generative models
WO2024172853A1 (en) 2023-02-17 2024-08-22 Unlearn. Ai, Inc. Systems and methods enabling baseline prediction correction
US11868900B1 (en) 2023-02-22 2024-01-09 Unlearn.AI, Inc. Systems and methods for training predictive models that ignore missing features

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP0360674A2 (en) * 1988-09-17 1990-03-28 Sony Corporation Signal processing system and learning processing system
US20120072215A1 (en) * 2010-09-21 2012-03-22 Microsoft Corporation Full-sequence training of deep structures for speech recognition

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7424270B2 (en) * 2002-09-25 2008-09-09 Qualcomm Incorporated Feedback decoding techniques in a wireless communications system
EP1638042A2 (en) * 2005-09-14 2006-03-22 Neal E. Solomon Mobile hybrid software router
US8762358B2 (en) * 2006-04-19 2014-06-24 Google Inc. Query language determination using query terms and interface language
US20100169328A1 (en) * 2008-12-31 2010-07-01 Strands, Inc. Systems and methods for making recommendations using model-based collaborative filtering with user communities and items collections
US9287713B2 (en) * 2011-08-04 2016-03-15 Siemens Aktiengesellschaft Topology identification in distribution network with limited measurements
US10453479B2 (en) * 2011-09-23 2019-10-22 Lessac Technologies, Inc. Methods for aligning expressive speech utterances with text and systems therefor
US20130325770A1 (en) * 2012-06-05 2013-12-05 Sap Ag Probabilistic language model in contextual network

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP0360674A2 (en) * 1988-09-17 1990-03-28 Sony Corporation Signal processing system and learning processing system
US20120072215A1 (en) * 2010-09-21 2012-03-22 Microsoft Corporation Full-sequence training of deep structures for speech recognition

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
DANILO JIMENEZ REZENDE ET AL: "Stochastic Backpropagation and Approximate Inference in Deep Generative Models", 16 January 2014 (2014-01-16), XP055159172, Retrieved from the Internet <URL:http://arxiv.org/abs/1401.4082> *
MARC'AURELIO RANZATO ET AL: "On deep generative models with applications to recognition", COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2011 IEEE CONFERENCE ON, IEEE, 20 June 2011 (2011-06-20), pages 2857 - 2864, XP032038212, ISBN: 978-1-4577-0394-2, DOI: 10.1109/CVPR.2011.5995710 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107291690A (en) * 2017-05-26 2017-10-24 北京搜狗科技发展有限公司 Punctuate adding method and device, the device added for punctuate
CN107291690B (en) * 2017-05-26 2020-10-27 北京搜狗科技发展有限公司 Punctuation adding method and device and punctuation adding device

Also Published As

Publication number Publication date
CN105144203A (en) 2015-12-09
US20140279777A1 (en) 2014-09-18
GB2513105A (en) 2014-10-22
GB201304795D0 (en) 2013-05-01
US9342781B2 (en) 2016-05-17
EP2973241B1 (en) 2020-10-21
WO2014140541A2 (en) 2014-09-18
CN105144203B (en) 2018-09-07
EP2973241A2 (en) 2016-01-20

Similar Documents

Publication Publication Date Title
WO2014140541A3 (en) Signal processing systems
MX2017013500A (en) Inventory information distribution systems, devices and methods.
RU2015106668A (en) TROUBLESHOOTING DIFFERENTIAL DYNAMIC TEAMS
SG11201907942QA (en) Blockchain cluster processing system and method, computer device and storage medium
WO2014143208A8 (en) Systems, methods and apparatuses for implementing data upload, processing, and predictive query api exposure
WO2015160713A3 (en) Platform for providing customizable user activity experiences
MY208279A (en) Electronic device and method for providing guide information based on genetic information
WO2014004524A3 (en) Notification classification and display
GB2550798A (en) Order pairing system and method
WO2015066489A3 (en) Efficient implementations for mapreduce systems
WO2016018472A3 (en) Content-based association of device to user
IN2013CH05115A (en)
WO2015134544A3 (en) Converter device and system including converter device
RU2014112950A (en) SYSTEM FOR DISPLAYING FUNCTIONS ON THE USER VEHICLE INTERFACE
MX2015000304A (en) Systems and methods for quantitative evaluation of a property for renovation.
TW201612743A (en) Bit group interleave processors, methods, systems, and instructions
WO2015114207A3 (en) Display management solution
PH12017500234B1 (en) Information-processing system
EA201791342A1 (en) INTERFACE METHOD AND COMPUTER SOFTWARE PRODUCT FOR MANAGING ELECTRONIC TRANSMISSION TRANSFER
WO2014165208A3 (en) Meter reading data validation
GB2571686A (en) System and method for analyzing and associating elements of a computer system by shared characteristics
GB2531678A (en) Moving objects in primary computer based on memory errors in secondary computer
WO2014080872A3 (en) Logic configuration method for reconfigurable semiconductor device
EP3101598A3 (en) Augmented neural networks
GB2541620A (en) Electrical system for universal charging station

Legal Events

Date Code Title Description
WWE Wipo information: entry into national phase

Ref document number: 201480016209.5

Country of ref document: CN

121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 14715977

Country of ref document: EP

Kind code of ref document: A2

WWE Wipo information: entry into national phase

Ref document number: 2014715977

Country of ref document: EP